Biosystems Engineering最新文献

In the food packaging industry, ventilated corrugated paperboard boxes are crucial for sustainable transport of fresh products. While these boxes' ventilation holes advance air circulation, they also impact the material's compression or buckling strength. Variations in hole geometry and location affecting this strength are explored, considering the composite material, multi-layered structure. Traditional mechanical analyses, which often require simplifications, may not fully capture this complexity, leading to less accurate predictions of the paperboard's strength. To address these challenges, a machine learning (ML) approach was utilized, employing the Light Gradient Boosting Machine (LGBM) to develop a predictive model for the buckling strength of corrugated paperboard boxes with ventilation cutouts. This physics-informed ML model, trained on a compression dataset resulting from experimental tests for plates with a single cutout in three shapes and Finite Element Method (FEM) simulations for plates with various patterns of circular cutouts, provides highly accurate estimates of the plates' buckling strength. It achieved 91.7% accuracy on experimental data and 94.68% on FEM simulation data, showcasing its reliability. A new tool for predicting the buckling strength of corrugated paperboard is provided by this research, along with insights that can inform the design of more sustainable packaging solutions. Furthermore, the methodology and findings have broader applications, potentially benefiting sectors like aerospace and construction, where similar structural materials are used.

It is important to develop low-cost, fast and portable meat adulteration detection systems to ensure the meat authenticity and safety in complex market environments. A multi-channel spectral detection system for meat adulteration was developed in this study. The core hardware of the system mainly includes a designed spectral module and a Raspberry pi controller. The spectral module consists of three multi-channel spectral sensors and LED lamps with specific wavelengths, containing 18 channels covering a range of 410–940 nm. The software was developed based on PyQt5. After completing the construction of the system, the detection distance was discussed and determined to be 4 mm. Based on the spectral data collected by the developed system, the models for classifying pure mutton, pure pork, mutton flavour essence adulteration, colourant adulteration and adulterated mutton with pork were established and compared. Four intelligent optimisation algorithms were further used to improve the model performance. The results of the test set showed that the support vector classification (SVC) model optimised by a sparrow search algorithm (SSA) obtained the best classification performance, with an accuracy of 97.59% and a Kappa coefficient of 0.9696. After the SSA-SVC was incorporated into the sensor software, the system performance was evaluated using external validation samples. The overall accuracy of the system was 94.29%. The system took about 5.31 s to detect a sample, and the total weight of the system was 1.55 kg. Overall, the developed portable spectral system has considerable potential to rapidly and accurately discriminate adulterated mutton in the field.

Quantifying seedling emergence pressure or forces (soil impedance to seedling) during the process of plant emergence is difficult in a practical setting. In this study, a mechanical seedling testing device was designed and calibrated to measure seedling emergence pressures experienced by conical or spherical mechanical seedling in soil with varying compaction levels. The data were analysed to generate regression models for predicting seedling emergence forces. Results showed a high correlation between the seedling emergence pressure and soil resistance. The resultant regression model produced a coefficient of determination (R²) of 0.99. After incorporating the morphological characteristics of soybean cotyledon and maize coleoptile into the model, the predicted seedling emergence forces increased with the soil compaction level. During the emergence process, average emergence force of the soybean seedlings was 11.8 N for the lowest compaction level and 28.5 N for the highest compaction level, and the corresponding values of the maize seedlings were 0.2 N and 0.6 N. In a non-compacted field plot, maize crop had a 95.4% emergence rate and soybean crop had 97.2%, whereas for a compacted plot, the corresponding emergence rates were decreased to 19.1% and 60.5%. Inferences made from the study provide information on the dynamics of soil-seedling interaction, which have important implications for managing soil compaction in crop production.

In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained R_P² of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (R_P² = 0.85) compared to RF bands (R_P² = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with R_P² of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved R_P² above 0.93 in individual years (R_P² = 0.96 in 2021, R_P² = 0.94 in 2021) and R_P² in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation.

Monitoring the number of cotton flowers can provide important information for breeders to assess the flowering time and the productivity of genotypes because flowering marks the transition from vegetative growth to reproductive growth and impacts the final yield. Traditional manual counting methods are time-consuming and impractical for large-scale fields. To count cotton flowers efficiently and accurately, a multi-view multi-object tracking approach was proposed by using both RGB and depth images collected by three RGB-D cameras fixed on a ground robotic platform. The tracking-by-detection algorithm was employed to track flowers from three views simultaneously and remove duplicated counting from single views. Specifically, an object detection model (YOLOv8) was trained to detect flowers in RGB images and a deep learning-based optical flow model Recurrent All-pairs Field Transforms (RAFT) was used to estimate motion between two adjacent frames. The intersection over union and distance costs were employed to associate flowers in the tracking algorithm. Additionally, tracked flowers were segmented in RGB images and the depth of each flower was obtained from the corresponding depth image. Those flowers tracked with known depth from two side views were then projected onto the middle image coordinate using camera calibration parameters. Finally, a constrained hierarchy clustering algorithm clustered all flowers in the middle image coordinate to remove duplicated counting from three views. The results showed that the mean average precision of trained YOLOv8x was 96.4%. The counting results of the developed method were highly correlated with those counted manually with a coefficient of determination of 0.92. Besides, the mean absolute percentage error of all 25 testing videos was 6.22%. The predicted cumulative flower number of Pima cotton flowers is higher than that of Acala Maxxa, which is consistent with what breeders have observed. Furthermore, the developed method can also obtain the flower number distributions of different genotypes without laborious manual counting in the field. Overall, the three-view approach provides an efficient and effective approach to count cotton flowers from multiple views. By collecting the video data continuously, this method is beneficial for breeders to dissect genetic mechanisms of flowering time with unprecedented spatial and temporal resolution, also providing a means to discern genetic differences in fecundity, the number of flowers that result in harvestable bolls. The code and datasets used in this paper can be accessed on GitHub: https://github.com/UGA-BSAIL/Multi-view_flower_counting.

Robots in tomato greenhouses need to perceive the plant and plant parts accurately to automate monitoring, harvesting, and de-leafing tasks. Existing perception systems struggle with the high levels of occlusion in plants and often result in poor perception accuracy. One reason for this is because they use fixed cameras or predefined camera movements. Next-best-view (NBV) planning presents an alternate approach, in which the camera viewpoints are reasoned and strategically planned such that the perception accuracy is improved. However, existing NBV-planning algorithms are agnostic to the task-at-hand and give equal importance to all the plant parts. This strategy is inefficient for greenhouse tasks that require targeted perception of specific plant parts, such as the perception of leaf nodes for de-leafing. To improve targeted perception in complex greenhouse environments, NBV planning algorithms need an attention mechanism to focus on the task-relevant plant parts. In this paper, the role of attention in improving targeted perception using an attention-driven NBV planning strategy was investigated. Through simulation experiments using plants with high levels of occlusion and structural complexity, it was shown that focusing attention on task-relevant plant parts can significantly improve the speed and accuracy of 3D reconstruction. Further, with real-world experiments, it was shown that these benefits extend to complex greenhouse conditions with natural variation and occlusion, natural illumination, sensor noise, and uncertainty in camera poses. The results clearly indicate that using attention-driven NBV planning in greenhouses can significantly improve the efficiency of perception and enhance the performance of robotic systems in greenhouse crop production.

A design was proposed for a seed turbine installed within the distribution device to reduce the influence of surface slope variations on the uniformity of seeding mass at each row. Through a comparative analysis based on the computational fluid dynamics (CFD) 6 degrees of freedom (DOF) dynamic mesh model simulation and the bench test, the influence of five different stabilising turbines on airflow distribution performance was investigated. The type Ⅰ stabilising turbine, characterised by acute inlet and outlet angles, exhibited a smaller vortex region at the blade inlet and improved the conveying and mixing performance of the seed. A CFD 6DOF simulation experiment was conducted to investigate the influence of the type I stabilising turbine on the airflow field distribution. As the number of blades increased from 4 to 10, the stability and uniformity of the conveying airflow distribution were enhanced at the turbine outlet. Simulations using a comprehensive performance test platform of the planter evaluated the influence of stabilising turbines with different numbers of blades on uniformity during field operations at varying surface slopes. When the angles of the front-rear and lateral one-way oscillation combination, and the front-rear and lateral reciprocating oscillation combination varied within the range of −5°–5°, the stabilising turbine with 8 blades exhibited the smallest uniformity coefficient of variation of the seeding mass at each row. The values ranged from 4.1 % to 5.8 % for rapeseeds and from 3.8 % to 5.0 % for wheat seeds.

In this study, a new microwave infrared hot air rolling bed dryer (MIHRBD) was developed and computational fluid dynamics (CFD) techniques were introduced into the design process of the integrated drying system. The structure of the air distribution device was optimised to improve the airflow uniformity over the curved surface of the rolling bed in the microwave-hot air drying combined equipment. The research findings reveal that, across eleven models, the outlet airflow velocity stabilises once the number of mesh elements reaches 5 million, achieving significant computational accuracy at that point. Optimizing components like the uniform air distribution pipe, turbulence plates, and wind deflectors significantly enhanced airflow distribution uniformity by 52.1%. The best airflow and temperature distribution uniformity on the rolling bed surface was achieved when the inlet airflow velocity ranged from 1 to 3 m s⁻¹, with minimum V_d, U_v and temperature non-uniformity coefficients of 0.007 m s⁻¹, 7.2% and 0.2%, respectively. Validation tests on the MIHRBD pilot equipment showed that after optimizing the uniform air distribution device, the minimum temperature difference on the pleurotus eryngii surface was 3.1 °C. This confirmed the feasibility of the computational fluid dynamics method. Introducing hot air significantly enhanced pleurotus eryngii's drying uniformity, with the Page model effectively predicting the MIHRBD drying process. This study provides technical support for future developments in this field of equipment manufacturing and drying process analysis.

In this study, a novel microwave sensing system, consisting of a microstrip self-resonant spiral coil inductively coupled to an external concentric planar probe loop, is presented and applied to the non-destructive detection of morpho-physiological plant responses to water stress. The optimised set-up of the proposed sensor ensures a highly sensitive spiral coil, which is a fundamental requirement to derive accurate information on plants' behavioural alterations related to water stress conditions. The proposed microwave sensor was tested it on two potted maize cultivars (Zea mays L.), namely “Cinquantino Bianchi” (CB) and “Scagliolo Frassine” (SF). For each cultivar, half of the samples were maintained at 100% (T100) field capacity while the other half was at 25% (T25) from 46 to 74 Days After Sowing (DAS). The frequency ($f_r$) shift and the amplitude peaks variation of the real component of the external planar probe input impedance (ℜ($Z_{input}$)) were obtained daily by positioning the sensor on the stem. These measured data were related to morpho-physiological parameters destructively acquired at four different growth stages. The resulting linear correlation between the stem's freshwater content (${FWC}_{stem}$) with both $f_r$ (r > −0.64) and the amplitude peaks (ℜ ($Z_{input}$)) (r > -0.70) provided evidence of the sensor's ability to identify stem dielectric properties' variations between the two water treatments. Concurrently, the sensor response demonstrated the capability to identify changes in the morphology and histology of the stem. Based on preliminary findings, the proposed sensor shows potential for employment in the real-time monitoring of plant water status, contributing to more economically and environmentally sustainable crop management practices. While the current correlations between plant water content and sensor measurements require further refinement to meet the rigorous industrial standards, nevertheless a large-scale adoption can be envisioned by leveraging IoT methodologies.

Emitter clogging adversely affects the performance of drip-irrigation systems. Many studies overlook the primary reason for emitter clogging by substances that precipitate within the emitter inlet. This study used computational fluid dynamics (CFD) to analyse the process of sedimentation in the inlet of emitters. Subsequently, the inlet structure was optimised based on the simulation results, production demand, and produced dripline. Anti-clogging physical tests were conducted in the laboratory and verified. Simulation results revealed that compared to the maximum discharge at the inlet of the domestic (CM) and Netafim (NF) emitters, that of the optimised (OS) emitter was increased by 60.0% and 13.2%, respectively; the maximum turbulent kinetic energy was increased by 88.9% and 13.3%, respectively; and the escape rate of solid particles in the dripline was increased by 3.2 and 5.9%, respectively. The results of an eighth-stage laboratory experiment with particle size ranges from 0.045 to 0.25 mm showed that the solid concentration was 1400 mg l⁻¹ for the CM-type emitter and 200 mg l⁻¹ for the OS-type emitter. However, the relative discharge of the OS-type emitter increased by 17.5%. At the end of the anti-clogging test, the relative discharge of the OS-type emitter was 0.12% more than that of the NF-type emitter. The water flowing through the OS-type emitter had a lower sediment content and higher relative discharge than of both comparison emitters. Therefore, optimising the emitter inlet can be an effective physical method for reducing the entry of solid particles into the emitter channel, which can greatly promote the sustainable development of drip irrigation.